@pasko70/pibo 1.4.1 → 1.4.3

package/context/pibo-system-prompt.md

@@ -1,78 +1,78 @@
-# Agent System
-
-You are an expert coding assistant operating inside pi, a coding agent harness. You help users by reading files, executing commands, editing code, and writing new files.
-
-## Tools
-
-Available tools:
-{{availableTools}}
-
-In addition to the tools above, you may have access to other custom tools depending on the project.
-
-## Guidelines
-
-{{guidelines}}
-
-Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
-
-**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
-
-## 1. Think Before Coding
-
-**Don't assume. Don't hide confusion. Surface tradeoffs.**
-
-Before implementing:
-- State your assumptions explicitly. If uncertain, ask.
-- If multiple interpretations exist, present them - don't pick silently.
-- If a simpler approach exists, say so. Push back when warranted.
-- If something is unclear, stop. Name what's confusing. Ask.
-
-## 2. Simplicity First
-
-**Minimum code that solves the problem. Nothing speculative.**
-
-- No features beyond what was asked.
-- No abstractions for single-use code.
-- No "flexibility" or "configurability" that wasn't requested.
-- No error handling for impossible scenarios.
-- If you write 200 lines and it could be 50, rewrite it.
-
-Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
-
-## 3. Surgical Changes
-
-**Touch only what you must. Clean up only your own mess.**
-
-When editing existing code:
-- Don't "improve" adjacent code, comments, or formatting.
-- Don't refactor things that aren't broken.
-- Match existing style, even if you'd do it differently.
-- If you notice unrelated dead code, mention it - don't delete it.
-
-When your changes create orphans:
-- Remove imports/variables/functions that YOUR changes made unused.
-- Don't remove pre-existing dead code unless asked.
-
-The test: Every changed line should trace directly to the user's request.
-
-## 4. Goal-Driven Execution
-
-**Define success criteria. Loop until verified.**
-
-Transform tasks into verifiable goals:
-- "Add validation" → "Write tests for invalid inputs, then make them pass"
-- "Fix the bug" → "Write a test that reproduces it, then make it pass"
-- "Refactor X" → "Ensure tests pass before and after"
-
-For multi-step tasks, state a brief plan:
-```
-1. [Step] → verify: [check]
-2. [Step] → verify: [check]
-3. [Step] → verify: [check]
-```
-
-Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
-
----
-
+# Agent System
+
+You are an expert coding assistant operating inside pi, a coding agent harness. You help users by reading files, executing commands, editing code, and writing new files.
+
+## Tools
+
+Available tools:
+{{availableTools}}
+
+In addition to the tools above, you may have access to other custom tools depending on the project.
+
+## Guidelines
+
+{{guidelines}}
+
+Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
+
+**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+## 1. Think Before Coding
+
+**Don't assume. Don't hide confusion. Surface tradeoffs.**
+
+Before implementing:
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them - don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+## 2. Simplicity First
+
+**Minimum code that solves the problem. Nothing speculative.**
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+## 3. Surgical Changes
+
+**Touch only what you must. Clean up only your own mess.**
+
+When editing existing code:
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it - don't delete it.
+
+When your changes create orphans:
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: Every changed line should trace directly to the user's request.
+
+## 4. Goal-Driven Execution
+
+**Define success criteria. Loop until verified.**
+
+Transform tasks into verifiable goals:
+- "Add validation" → "Write tests for invalid inputs, then make them pass"
+- "Fix the bug" → "Write a test that reproduces it, then make it pass"
+- "Refactor X" → "Ensure tests pass before and after"
+
+For multi-step tasks, state a brief plan:
+```
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+```
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
+
+---
+
 **These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.

package/dist/apps/chat/agent-store.js

@@ -17,35 +17,35 @@ export class CustomAgentStore {
         this.db.exec("PRAGMA busy_timeout = 5000");
         if (resolvedPath !== ":memory:")
             this.db.exec("PRAGMA journal_mode = WAL");
-        this.db.exec(`
-			CREATE TABLE IF NOT EXISTS chat_agents (
-				id TEXT PRIMARY KEY,
-				profile_name TEXT NOT NULL UNIQUE,
-				display_name TEXT NOT NULL,
-				description TEXT,
-				native_tools_json TEXT NOT NULL,
-				skills_json TEXT NOT NULL,
-				context_files_json TEXT NOT NULL,
-				subagents_json TEXT NOT NULL,
-				mcp_servers_json TEXT NOT NULL DEFAULT '[]',
-				pi_packages_json TEXT NOT NULL DEFAULT '[]',
-				main_model_json TEXT,
-				subagent_model_json TEXT,
-				thinking_level TEXT,
-				main_thinking_level TEXT,
-				subagent_thinking_level TEXT,
-				fast INTEGER,
-				main_fast INTEGER,
-				subagent_fast INTEGER,
-				builtin_tools TEXT NOT NULL,
-				builtin_tool_names_json TEXT NOT NULL DEFAULT '["read","bash","edit","write"]',
-				auto_context_files INTEGER NOT NULL DEFAULT 1,
-				run_control INTEGER NOT NULL,
-				created_at TEXT NOT NULL,
-				updated_at TEXT NOT NULL,
-				archived_at TEXT
-			);
-
+        this.db.exec(`
+			CREATE TABLE IF NOT EXISTS chat_agents (
+				id TEXT PRIMARY KEY,
+				profile_name TEXT NOT NULL UNIQUE,
+				display_name TEXT NOT NULL,
+				description TEXT,
+				native_tools_json TEXT NOT NULL,
+				skills_json TEXT NOT NULL,
+				context_files_json TEXT NOT NULL,
+				subagents_json TEXT NOT NULL,
+				mcp_servers_json TEXT NOT NULL DEFAULT '[]',
+				pi_packages_json TEXT NOT NULL DEFAULT '[]',
+				main_model_json TEXT,
+				subagent_model_json TEXT,
+				thinking_level TEXT,
+				main_thinking_level TEXT,
+				subagent_thinking_level TEXT,
+				fast INTEGER,
+				main_fast INTEGER,
+				subagent_fast INTEGER,
+				builtin_tools TEXT NOT NULL,
+				builtin_tool_names_json TEXT NOT NULL DEFAULT '["read","bash","edit","write"]',
+				auto_context_files INTEGER NOT NULL DEFAULT 1,
+				run_control INTEGER NOT NULL,
+				created_at TEXT NOT NULL,
+				updated_at TEXT NOT NULL,
+				archived_at TEXT
+			);
+
 		`);
         this.migrateArchivedAtColumn();
         this.migrateAutoContextFilesColumn();
@@ -141,31 +141,31 @@ export class CustomAgentStore {
             updatedAt: new Date().toISOString(),
         };
         this.db
-            .prepare(`
-				UPDATE chat_agents SET
-					profile_name = ?,
-					display_name = ?,
-					description = ?,
-					native_tools_json = ?,
-					skills_json = ?,
-					context_files_json = ?,
-					subagents_json = ?,
-					mcp_servers_json = ?,
-					pi_packages_json = ?,
-					main_model_json = ?,
-					subagent_model_json = ?,
-					thinking_level = ?,
-					main_thinking_level = ?,
-					subagent_thinking_level = ?,
-					fast = ?,
-					main_fast = ?,
-					subagent_fast = ?,
-					builtin_tools = ?,
-					builtin_tool_names_json = ?,
-					auto_context_files = ?,
-					run_control = ?,
-					updated_at = ?
-				WHERE id = ?
+            .prepare(`
+				UPDATE chat_agents SET
+					profile_name = ?,
+					display_name = ?,
+					description = ?,
+					native_tools_json = ?,
+					skills_json = ?,
+					context_files_json = ?,
+					subagents_json = ?,
+					mcp_servers_json = ?,
+					pi_packages_json = ?,
+					main_model_json = ?,
+					subagent_model_json = ?,
+					thinking_level = ?,
+					main_thinking_level = ?,
+					subagent_thinking_level = ?,
+					fast = ?,
+					main_fast = ?,
+					subagent_fast = ?,
+					builtin_tools = ?,
+					builtin_tool_names_json = ?,
+					auto_context_files = ?,
+					run_control = ?,
+					updated_at = ?
+				WHERE id = ?
 			`)
             .run(updated.profileName, updated.displayName, updated.description ?? null, JSON.stringify(updated.nativeTools), JSON.stringify(updated.skills), JSON.stringify(updated.contextFiles), JSON.stringify(sanitizeSubagents(updated.subagents)), JSON.stringify(updated.mcpServers), JSON.stringify(updated.piPackages), updated.mainModel ? JSON.stringify(updated.mainModel) : null, updated.subagentModel ? JSON.stringify(updated.subagentModel) : null, updated.thinkingLevel ?? null, updated.mainThinkingLevel ?? null, updated.subagentThinkingLevel ?? null, serializeBoolean(updated.fast), serializeBoolean(updated.mainFast), serializeBoolean(updated.subagentFast), updated.builtinTools, JSON.stringify(updated.builtinToolNames), updated.autoContextFiles ? 1 : 0, updated.runControl ? 1 : 0, updated.updatedAt, id);
         return this.get(id);
@@ -190,34 +190,34 @@ export class CustomAgentStore {
     }
     insert(agent) {
         this.db
-            .prepare(`
-				INSERT INTO chat_agents (
-					id,
-					profile_name,
-					display_name,
-					description,
-					native_tools_json,
-					skills_json,
-					context_files_json,
-					subagents_json,
-					mcp_servers_json,
-					pi_packages_json,
-					main_model_json,
-					subagent_model_json,
-					thinking_level,
-					main_thinking_level,
-					subagent_thinking_level,
-					fast,
-					main_fast,
-					subagent_fast,
-					builtin_tools,
-					builtin_tool_names_json,
-					auto_context_files,
-					run_control,
-					created_at,
-					updated_at,
-					archived_at
-				) VALUES (${Array.from({ length: 25 }, () => "?").join(", ")})
+            .prepare(`
+				INSERT INTO chat_agents (
+					id,
+					profile_name,
+					display_name,
+					description,
+					native_tools_json,
+					skills_json,
+					context_files_json,
+					subagents_json,
+					mcp_servers_json,
+					pi_packages_json,
+					main_model_json,
+					subagent_model_json,
+					thinking_level,
+					main_thinking_level,
+					subagent_thinking_level,
+					fast,
+					main_fast,
+					subagent_fast,
+					builtin_tools,
+					builtin_tool_names_json,
+					auto_context_files,
+					run_control,
+					created_at,
+					updated_at,
+					archived_at
+				) VALUES (${Array.from({ length: 25 }, () => "?").join(", ")})
 			`)
             .run(agent.id, agent.profileName, agent.displayName, agent.description ?? null, JSON.stringify(agent.nativeTools), JSON.stringify(agent.skills), JSON.stringify(agent.contextFiles), JSON.stringify(sanitizeSubagents(agent.subagents)), JSON.stringify(agent.mcpServers), JSON.stringify(agent.piPackages), agent.mainModel ? JSON.stringify(agent.mainModel) : null, agent.subagentModel ? JSON.stringify(agent.subagentModel) : null, agent.thinkingLevel ?? null, agent.mainThinkingLevel ?? null, agent.subagentThinkingLevel ?? null, serializeBoolean(agent.fast), serializeBoolean(agent.mainFast), serializeBoolean(agent.subagentFast), agent.builtinTools, JSON.stringify(agent.builtinToolNames), agent.autoContextFiles ? 1 : 0, agent.runControl ? 1 : 0, agent.createdAt, agent.updatedAt, agent.archivedAt ?? null);
     }